AI Paper Atlas

Research map / Image generation / Image restoration

DWDN: Deep Wiener Deconvolution Network for Non-Blind Image Deblurring

Jiangxin Dong, Stefan Roth, Bernt Schiele

TPAMI 2021 · Image generation › Image restoration · approach: Image deblurring · 105 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add feature-based Wiener deconvolution to the network (ablation)DWDN · Levin 1% noisePSNR: 25.70 -> 36.90Improved
add gradient features to intensity in classical Wiener deconvolution (ablation)Wiener_I · Levin 1% noisePSNR: 30.32 -> 33.37Improved
use 9 learned deep features instead of intensity plus gradients (ablation)Wiener_I+G · Levin 1% noisePSNR: 33.37 -> 34.09Improved
learn 16 deep features instead of 9 (ablation)Wiener_9 features · Levin 1% noisePSNR: 34.09 -> 34.78Improved
add multi-scale feature refinement on top of Wiener with deep features (ablation)Wiener_16 features · Levin 1% noisePSNR: 34.78 -> 36.90Improved
use learned deep features instead of input image + gradients (ablation)DWDN_I+G · Levin 1% noisePSNR: 36.52 -> 36.90Improved
use piecewise linear (ReLU) deep features instead of linear features (ablation)Wiener_16 features · Levin 1% noisePSNR: 33.69 -> 34.78Improved
add multi-scale refinement (ablation)DWDN · Levin kernels 53-59, 1% noisePSNR: 27.45 -> 27.73Improved
add 2 cascades (ablation)DWDN · Sun et al. 1% noisePSNR: 34.05 -> 34.27Improved
add 3 cascades (ablation)DWDN · Sun et al. 1% noisePSNR: 34.05 -> 34.47Improved
add residual learning in earlier cascade stages (ablation)DWDN+ · Sun et al. 1% noisePSNR: 34.47 -> 34.62Improved
train one noise-blind model instead of noise-specific models (ablation)DWDN · Levin 1% noisePSNR: 37.02 -> 36.90No clear effect

Later papers that compared with this method

3 later accepted papers report DWDN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy